Reading: CNN-CR — CNN for Image Compact-Resolution (HEVC Intra)

VDSR-Like Network, Outperforms EDSR & Li TCSVT’18

Outline

1. CNN-CR: Loss Function

CNN-CR: Loss Function
Different Values of λ

With the above loss function, image CR can generate a low-resolution image which can better preserve high frequency components of the original CR, so that when the CR image is upsampled, higher quality is obtained.

2. CNN-CR: Network Architecture

CNN-CR: Network Architecture
Different Network Depths
Different Downsizing
Residual Learning

3. Separate Training & Joint Training

Progressive Training

4. Application Realizations

(a) Frame-level down- and up-sampling coding scheme. (b) Block-level adaptive down- and up-sampling coding scheme

5. Experimental Results

PSNR on Test Sets
PSNR on Test Sets

6. Results for Image Retargeting

CNN-CRJoint is compared to seam carving and bicubic down-sampling, respectively.

7. Results for Image/Video Compression

RD Curves
BD-Rate
Hitting Ratios
Computational Complexity Using GPU

This is the 33rd story in this month!

--

--

PhD, Researcher. I share what I learn. :) Linktree: https://linktr.ee/shtsang for Twitter, LinkedIn, etc.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store